Introduction to Information Retrieval: | Guide books

Introduction to Information RetrievalJuly 2008

Go to Introduction to Information Retrieval

July 2008

Publisher:

Cambridge University Press
40 W. 20 St. New York, NY
United States

ISBN:978-0-521-86571-5

Published:07 July 2008

Pages:

496

Available at Amazon

Bibliometrics

Abstract

Class-tested and coherent, this groundbreaking new textbook teaches web-era information retrieval, including web search and the related areas of text classification and text clustering from basic concepts. Written from a computer science perspective by three leading experts in the field, it gives an up-to-date treatment of all aspects of the design and implementation of systems for gathering, indexing, and searching documents; methods for evaluating systems; and an introduction to the use of machine learning methods on text collections. All the important ideas are explained using examples and figures, making it perfect for introductory courses in information retrieval for advanced undergraduates and graduate students in computer science. Based on feedback from extensive classroom experience, the book has been carefully structured in order to make teaching more natural and effective. Although originally designed as the primary text for a graduate or advanced undergraduate course in information retrieval, the book will also create a buzz for researchers and professionals alike.

Cited By

Contributors

Chris Manning
Stanford University
- Publication Years1993 - 2023
- Publication counts142
- Citation count10,651
- Available for Download109
- Downloads (cumulative)129,537
- Downloads (12 months)8,583
- Downloads (6 weeks)1,818
- Average Downloads per Article1,188
- Average Citation per Article75
View Full Profile
Prabhakar Raghavan
Yahoo Research Labs
- Publication Years1983 - 2013
- Publication counts175
- Citation count16,603
- Available for Download73
- Downloads (cumulative)103,410
- Downloads (12 months)6,838
- Downloads (6 weeks)1,135
- Average Downloads per Article1,417
- Average Citation per Article95
View Full Profile
Hinrich Schütze
Ludwig-Maximilians-University Munich
- Publication Years1991 - 2022
- Publication counts81
- Citation count6,088
- Available for Download55
- Downloads (cumulative)29,153
- Downloads (12 months)999
- Downloads (6 weeks)171
- Average Downloads per Article530
- Average Citation per Article75
View Full Profile

Index Terms

Introduction to Information Retrieval

Recommendations

Reviewer: George Pallis

As the back cover notes, this book offers a unique approach to the important topic of information retrieval (IR) by providing mathematical foundations based on modern algebra, specifically lattice theory. Dominich is eminently qualified as the leader of several workshops on the mathematical foundations of information retrieval held at the ACM SIGIR conferences. The book starts with an introduction to IR modeling, followed by an introduction to modern algebra, including logic, Boolean logic, set theory, fuzzy set theory, and, of course, lattice theory. This is followed by a more detailed look at IR, looking at such issues as: stop lists and stemming for keywords; term-document matrices; the Web with its metadata, search, and metasearch engines; indexing; and even computer architecture for IR. Moreover, IR performance measures are discussed. Dominich then provides a fresh look at IR using lattice theory; this is the heart of the contributions made by the book. Then, the use of lattice theory for spaces and subspaces is introduced, in order to show how lattice theory can help generalize the various models of IR systems. The author commences with an examination of the mathematics of the well-known vector space model, the fuzzy retrieval model, and the well-known probabilistic model. Finally, retrieval on the Web is analyzed in detail using this foundation to look at ranking methodologies as well as other features of Web retrieval. I must note that I learned a lot about how some of the intricate mathematics can be well employed to help provide a fine foundation for those of us who have worked in IR. The acknowledgments section states that parts of the book were used in an undergraduate course taught by Dominich. I have no doubt that the good problems at the end of each chapter, as well as solutions to some of the problems, could be put to good use in such a course. One minor quibble that I have is that some of the authors mentioned in the text, including myself, are not found in the large bibliography placed at the end of the book. However, in spite of that, I can easily recommend this book as a reference for any of the technical IR courses offered at several universities. Online Computing Reviews Service

Reviewer: H. Van Dyke Parunak

The nature of information has changed profoundly over the last 50 years. Two dimensions of this change pose, respectively, a formidable challenge to users of information and a potential remedy to that problem. The challenge lies in the exponential growth of the amount of information. The information that has become available during the working lives of today's population far exceeds that generated in the previous history of the world. In 2007, for the first time, the amount of information replicated, generated, or captured exceeded the available storage. This rapid growth means that while the information we need to solve our most pressing problems is more likely than ever before to exist somewhere, the problem of finding it makes it effectively invisible. The potential remedy lies in the fact that most of the new information created each year is in digital form. Unlike the carved, written, or printed media that dominated information storage in the pre-digital age, the bulk of new information can be searched by computer. Even much of the old printed information is becoming searchable by machine, due to digitizing initiatives such as Project Gutenberg and Google Books. The research community has responded to this opportunity by developing a wide range of theories and algorithms to enable computerized retrieval of digital information. This volume is an introductory text to these technologies that is both reasonably comprehensive and eminently comprehensible. Although some of the pattern recognition techniques discussed are applicable to any digital data, the book's focus is on text. The first five chapters discuss the preparation and indexing of text, including the notion of an inverted index and how it can support both Boolean and ranked queries (chapter 1); deriving a term vocabulary-with an engaging discussion of the challenges of documents in mixed character encodings such as Arabic-Roman or Chinese-Roman (chapter 2); constructing dictionaries that are robust against misspellings and similar orthographic issues (chapter 3); and construction and compression of indices (chapters 4 and 5). These introductory chapters set the book apart from an abstract introduction to pattern recognition, by introducing the reader to the nuts and bolts of preparing a document collection for machine search and retrieval. Chapters 6 and 7 discuss quantitative measures of similarity between a query and a document, building on the venerable vector-space model. Chapter 8 uses these quantitative measures as the basis for evaluating an information retrieval system, describing widely used test corpora, and introducing scores such as precision, recall, accuracy, the F -measure, and the receiver operating characteristic (ROC) curve. The remainder of the chapters deal with a wide range of more specialized topics, in three broad areas: more refined query processing, classification as an alternative to querying for information retrieval, and Web searching. Chapter 9 discusses how relevance feedback from the user can help reformulate and refine queries. Chapter 10 explores how to search documents with nonlinear structure, specifically Extensible Markup Language (XML) files. Chapter 11 describes how to generate a probabilistic model of the match between document and query, rather than simply counting matching terms. Chapter 12 reviews how statistical models of language generation can yield a more refined statistical representation of documents and queries. Chapter 13 shifts from a query-oriented approach to retrieval to a classification perspective, in which documents are classified as they become available. Chapter 14 extends the vector-space model to classification. Chapter 15 introduces support vector machines (SVMs). Chapters 16 and 17 discuss flat and hierarchical clustering, respectively. Chapter 18 introduces latent semantic indexing, and the "further reading" section introduces more sophisticated probabilistic models such as the latent Dirichlet allocation. Increasingly, the information that people search lives not on document databases, but in hyperlinked Web pages. This environment poses special challenges that are introduced in chapter 19. Chapter 20 discusses Web crawling and what can and cannot be indexed in a dynamic environment. Chapter 21 reviews major approaches to link analysis, including Google's PageRank algorithm and the hub-and-authority model. Exercises are distributed throughout each chapter, graded for difficulty and, in some cases, with solutions. Each chapter has a discussion of related literature, identifying further details that are not covered in the text, along with readings where those ideas can be explored. The book has an extensive index and a cumulative bibliography of over 650 entries through 2007. This volume deserves wide and prolonged use, not only as a major text for classes on information retrieval, but also as a desk reference for practicing information professionals. Online Computing Reviews Service

Access critical reviews of Computing literature here

Become a reviewer for Computing Reviews.

Comments

Browse Books

Sections

Cited By

Index Terms

Information Retrieval: Implementing and Evaluating Search Engines

Information Retrieval: Implementing and Evaluating Search Engines

An Introduction to Neural Information Processing

Access critical reviews of Computing literature here

Save to Binder

Sections

Cited By

Save to Binder

Index Terms

Recommendations

Information Retrieval: Implementing and Evaluating Search Engines

Information Retrieval: Implementing and Evaluating Search Engines

An Introduction to Neural Information Processing

Access critical reviews of Computing literature here